Industrial equipment energy consumption intelligent monitoring method and system

Abstract

The embodiment of the invention relates to the technical field of information, in particular to an intelligent monitoring method and system for energy consumption of industrial equipment. The method comprises the following steps: acquiring a region monitoring video and region energy consumption data of a monitoring region and working sound data of each device, and segmenting a device monitoring video of each device region from the region monitoring video; identifying the working state of each device, and associating the initial energy consumption power; setting sampling points daily, calculating the sum of the energy consumption powers associated with the working states of all the equipment at the sampling point moments, and recording the sum as predicted power; calculating a difference value between the regional energy consumption data at the sampling points and the predicted power, recording the difference value as a sampling point difference value, and recording the sum of the difference values of all the sampling points as a total difference value; continuously adjusting the energy consumption power associated with each working state of each type of equipment until the total difference value is smaller than a preset value; and obtaining a monitoring result according to the real-time identified working state of each device and the associated energy consumption power.

Description

Technical Field

[0001] Multiple embodiments of this specification relate to the field of information technology, and specifically to an intelligent monitoring method and system for the energy consumption of industrial equipment. Background Art

[0002] Efficient and accurate monitoring and management of industrial equipment have become increasingly important. Among them, energy consumption monitoring, as a key link in optimizing the production process, reducing costs, and improving energy efficiency, has received extensive attention. Traditional energy consumption monitoring methods usually rely on simple electricity meter readings or preset energy consumption models. This method cannot accurately reflect the actual energy consumption of each device under different working conditions and is difficult to meet the requirements of modern industry for refined management. Some currently disclosed solutions improve the monitoring fineness by increasing the number of sensors or the data acquisition frequency, but this often comes with a significant increase in cost and poses higher requirements for data processing and analysis. Summary of the Invention

[0003] Multiple embodiments of this specification describe an intelligent monitoring method and system for the energy consumption of industrial equipment.

[0004] In a first aspect, an embodiment of this specification provides an intelligent monitoring method for the energy consumption of industrial equipment, including the steps of: Collecting the regional monitoring video, regional energy consumption data, and the working sound data of each device in the monitoring area, and cutting out the device monitoring video of each device area from the regional monitoring video; Identifying the working state of each device according to the device monitoring video and working sound data of each device, and associating an initial energy consumption power with each working state of each type of device; Setting sampling points by day, calculating the sum of the energy consumption powers associated with the working states of all devices at the sampling point moments, and recording it as the predicted power; Calculating the difference between the regional energy consumption data and the predicted power at the sampling point, recording it as the sampling point difference value, and recording the sum of all sampling point difference values as the total difference value; Continuously adjusting the energy consumption power associated with each working state of each type of device until the total difference value is less than a preset value; Obtaining the monitoring result according to the working state of each device recognized in real time and the associated energy consumption power.

[0005] In a second aspect, an embodiment of this specification provides an intelligent monitoring system for the energy consumption of industrial equipment, including: A collection module that collects the regional monitoring video, regional energy consumption data, and the working sound data of each device in the monitoring area, and cuts out the device monitoring video of each device area from the regional monitoring video; An identification module that identifies the working status of each device based on the device monitoring video and working sound data of each device, and associates an initial energy consumption power with each working status of each device; A first calculation module that sets sampling points daily and calculates the sum of the energy consumption powers associated with the working statuses of all devices at the sampling point moments, denoted as the predicted power; A second calculation module that calculates the difference between the regional energy consumption data at the sampling point and the predicted power, denoted as the sampling point difference value, and the sum of all sampling point difference values is denoted as the total difference value; An adjustment module that continuously adjusts the energy consumption power associated with each working status of each device until the total difference value is less than a preset value; A monitoring module that obtains a monitoring result based on the working status of each device identified in real time and the associated energy consumption power;

[0006] In a third aspect, an embodiment of this specification provides an electronic device, including a processor and a memory; The processor is connected to the memory; The memory is used to store executable program code; The processor runs a program corresponding to the executable program code by reading the executable program code stored in the memory, so as to execute the method described in any of the above aspects;

[0007] In a fourth aspect, an embodiment of this specification provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the method described in any of the above aspects is implemented;

[0008] In a fifth aspect, an embodiment of this specification provides a computer program product, including a computer program, and when the computer program is executed by a processor, the method described in any of the above aspects is implemented;

[0009] The beneficial effects brought by the technical solutions provided in some embodiments of this specification at least include: In multiple embodiments of this specification, the industrial equipment energy consumption intelligent monitoring method and system provided combine video monitoring, sound analysis, and energy consumption data to more accurately identify the working status of devices, and obtain the energy consumption situation of the monitoring area based on the energy consumption power associated with each working status. The accuracy of energy consumption prediction is significantly improved through the method of multi-source information fusion. Provide more refined energy monitoring, which can provide data reference for enterprises to better control operating costs. Abnormal high energy consumption is often an early signal of equipment failure, and potential equipment problems can be warned in advance by continuously monitoring energy consumption changes. More accurately grasping the operating status of each device and its corresponding energy consumption situation helps to optimize the processing process and also helps to ensure the stable operation of the production line.

[0010] The other features and advantages of the embodiments of this specification will be further revealed in the following detailed description and the accompanying drawings. Brief Description of the Drawings

[0011] In order to more clearly illustrate the technical solutions in the embodiments of this specification, the accompanying drawings required for the embodiments will be briefly introduced below. Obviously, the accompanying drawings in the following description are only some embodiments of this specification. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings.

[0012] Figure 1 Schematic diagram of the monitoring area for the energy consumption intelligent monitoring method provided by the embodiments of this specification.

[0013] Figure 2 Schematic diagram of the flow of the energy consumption intelligent monitoring method provided by the embodiments of this specification.

[0014] Figure 3 Schematic diagram of the device monitoring video provided by the embodiments of this specification.

[0015] Figure 4 Schematic diagram of the energy consumption intelligent monitoring system provided by the embodiments of this specification.

[0016] Figure 5 Schematic diagram of the electronic device provided by the embodiments of this specification. Detailed Description of the Embodiments

[0017] The technical solutions of the embodiments of this specification will be explained and illustrated below with reference to the accompanying drawings of the embodiments of this specification. However, the following embodiments are only the preferred embodiments of this specification, not all of them. Based on the embodiments in the implementation manners, other embodiments obtained by those of ordinary skill in the art without creative efforts all fall within the protection scope of this specification.

[0018] The terms "first", "second", "third", etc. in the specification, claims and the above accompanying drawings of this specification are used to distinguish different objects, rather than to describe a specific order. In addition, the terms "include" and "have" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product or device that includes a series of steps or units is not limited to the listed steps or units, but optionally further includes steps or units not listed, or optionally further includes other steps or units inherent to these processes, methods, products or devices.

[0019] In the following description, terms indicating orientation or positional relationships such as "inner", "outer", "upper", "lower", "left", "right", etc. are only for the convenience of describing embodiments and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be construed as a limitation of this specification.

[0020] The data involved in this application are all information and data authorized by users or fully authorized by all parties, and the collection, use, and processing of relevant data comply with the relevant laws, regulations, and standards of relevant countries and regions.

[0021] Before introducing the technical solutions described in this specification, the application scenarios of the technical solutions and related technologies are introduced.

[0022] This embodiment is recommended for use in the field of machining, such as energy monitoring in a CNC machining workshop. Please refer to the appendix Figure 1 , a CNC machining workshop is equipped with various types of equipment, such as CNC lathes, CNC milling machines, CNC machining centers, etc. These equipment have significantly different powers under different working states and operating conditions. Without an accurate energy consumption monitoring mechanism, it is difficult for managers to grasp the working state of each equipment and its corresponding energy consumption in real time. With the rising cost of electricity bills, effective management of energy use has become one of the key factors in controlling operating costs. Fine management of energy can help enterprises significantly reduce expenses and improve economic efficiency. In addition, a good energy management system can also help predict potential equipment failures. Abnormally high energy consumption may be an early signal of hardware failure. Identifying these problems in advance can avoid production interruptions caused by sudden equipment failures, which can improve the overall work efficiency and reliability. Applying an advanced energy monitoring system in a CNC machining workshop can not only help enterprises achieve the goal of energy conservation and emission reduction, but also bring direct economic benefits and contribute to the sustainable development of society.

[0023] The intelligent monitoring combining multiple means such as video monitoring and sound analysis disclosed in this specification provides a new technical solution for energy consumption monitoring.

[0024] First, this specification provides an intelligent monitoring method for the energy consumption of industrial equipment. Please refer to the appendix Figure 2 , including the steps: Step S01) Collect the regional monitoring video, regional energy consumption data, and the working sound data of each device in the monitoring area 10, and cut out the device monitoring video 11 of each device area from the regional monitoring video. Please refer to the appendix Figure 3, the device monitoring video 11 needs to show the images of the moving parts of the industrial device. It is allowed that the video monitoring angles of the same type of industrial devices are different. When the angles are different, the images of the same parts will be different, but they can all be recognized through image recognition. For this reason, it is necessary to install multiple video monitoring devices in the monitoring area 10 and a video monitoring device at each industrial device. The technical solutions described in this specification require low clarity and resolution for the video monitoring devices, so relatively low-cost cameras can be used to complete them, and the cost increase is not obvious. The sound collection can be completed by a camera with sound collection function or by using a separate microphone.

[0025] Step S02) According to the device monitoring video 11 and the working sound data of each device, identify the working state of each device, and associate the initial energy consumption power with each working state of each device.

[0026] The method for identifying the working state of each device according to the device monitoring video 11 and the working sound data of each device includes: Identify the moving parts of the device according to the device monitoring video 11 to obtain the moving part time sequence table; Segment the device monitoring video 11 according to the moving part time sequence table, and each segment corresponds to a working state; Assign a unique identification name to each working state, and use the identification name as the working state of the segment.

[0027] Among them, the method for identifying the moving parts of the device according to the device monitoring video 11 to obtain the moving part time sequence table includes: Read the device monitoring video 11 containing the actions of all the moving parts of the device, and receive the range annotation and part name annotation of the moving parts manually marked; Establish a part image recognition model according to the range annotation and part name annotation; Identify the parts in each frame according to the frame image of the device monitoring video 11 and the part image recognition model; Judge whether the part is moving according to the range of the part in each frame to obtain the moving parts; The part names and action time sequences of all the identified moving parts constitute the moving part time sequence table.

[0028] Taking a CNC lathe as an example, a video containing the activities of all moving parts of the CNC lathe is read. Exemplarily, it includes spindle rotation, tool feeding, fixture fixing, etc. The ranges and names of the moving parts are manually marked, and then a component image recognition model capable of identifying the moving parts is established. Using the component image recognition model, each component in the video is recognized based on each frame of the image, and it is determined whether it is in an operating state. All the recognized moving parts and their action sequences form an action component time sequence table.

[0029] Then, the equipment monitoring video 11 is segmented according to the action component time sequence table. Each segment represents a specific process or working state executed by the CNC lathe. For example, in the operation of a CNC lathe, it may include multiple processes such as workpiece clamping, rough turning, finish turning, drilling, grooving, etc. Each process corresponds to a series of specific combinations of moving part operations, such as spindle start, tool moving to a specified position to start machining, etc. Exemplarily, the action component time sequence table for rough turning is: {spindle rotation, turret movement, tool feeding, coolant start, tool withdrawal, coolant stop, turret reset}.

[0030] In fact, the action component time sequence tables for rough turning, finish turning, and grooving are the same. Therefore, it is necessary to further distinguish them by combining the working sound data.

[0031] Specifically, the working sound data corresponding to each working state of the equipment is read, the features of the working sound data are extracted, and the sound data is classified according to the features. When there are multiple classifications of the working sound data corresponding to the working state, a suffix number is associated with each classification of the working sound data. The working state is split into multiple working states according to the classification of the sound data, and the identification name and the corresponding suffix number are associated.

[0032] Each working state is assigned a unique identification name, and this identification name is used as the working state of the segment. For example, workpiece clamping, rough turning, finish turning, drilling, grooving, etc. can all be given identification names. This not only facilitates the management and tracking of the status of each process but also provides convenience for subsequent data analysis. For example, in the rough turning stage, the identification name can help us quickly locate the corresponding video segment of this stage, as well as the associated energy consumption data and sound feature data.

[0033] Combined with the real-time collected working sound data, the working states can be distinguished more accurately. Specifically, rough turning will have a higher noise level and also a relatively large energy consumption value. While finish turning is relatively quiet and has a lower corresponding energy consumption. Through comprehensive analysis of these data, the actual operating conditions of the CNC lathe under different processes can be understood more precisely, thereby providing a basis for optimizing the machining process and improving production efficiency. In addition, it can also help predict potential mechanical failures, take measures in advance to avoid downtime, and ensure the continuity and stability of production.

[0034] Among them, the method for establishing a component image recognition model according to the range annotation and component name annotation includes: Obtain the image of the component according to the range annotation, associate the image with the component name, and obtain sample data; Establish an image recognition model and use the sample data to train the image recognition model; According to the trained image recognition model, obtain the component image recognition model.

[0035] For the manual range annotation and component name annotation of the components in the equipment monitoring video 11, extract the images of the components. Each image is associated with the corresponding component name to form a sample data set. For example, in the rough turning stage, the action intervals of the spindle, chuck, and tool can be annotated, and images in different states can be collected. Use the sample data with annotation information to establish an image recognition model. Select a machine learning model according to the publicly available technologies in the field. Exemplarily, such as a convolutional neural network (CNN). By inputting the sample data into the machine learning model, the machine learning model can achieve the recognition of components.

[0036] On the other hand, in another embodiment, collect the equipment monitoring video 11 from multiple angles, The method for establishing a component image recognition model according to the range annotation and component name annotation includes: Obtain multiple-angle images of the component according to the range annotation, associate the images with the component name, and obtain sample data; Establish an image recognition model and use the sample data to train the image recognition model; According to the trained image recognition model, obtain the component image recognition model.

[0037] The sample data from multiple angles can enhance the extensibility of the model and make the recognition more accurate.

[0038] On the other hand, the method for extracting the features of the working sound data and classifying the sound data according to the features includes: Segment the working sound data according to a preset time length to obtain multiple sound sample data; Build an autoencoder model and train the autoencoder model using the sound sample data; Obtain a feature extraction model according to the autoencoder model; Extract the features of the working sound data using the feature extraction model; Receive the manually added load degree annotation as an associated label to obtain sound feature sample data; Build and train a machine learning model using the sound feature sample data to obtain a sound data classification model; Extract the features of the subsequently collected working sound data and classify the sound data according to the sound data classification model.

[0039] Segment the collected working sound data according to a preset time length. Exemplarily, each segment lasts for 1 second or 2 seconds to obtain multiple sound sample data. The multiple sound sample data cover the working sounds of the device in different working states.

[0040] Build an autoencoder model and train it using sound sample data. An autoencoder is an unsupervised learning model that can learn the latent feature representation of sound data through an encoding-decoding structure. After training, the encoding part in the autoencoder model can be extracted as the feature extraction model.

[0041] Use this feature extraction model to process all sound samples and extract the low-dimensional feature vectors of each segment of sound. These low-dimensional feature vectors reflect the essential characteristics of the sound signal. Receive the manually added load degree annotation as the label information related to the sound features. Pair the extracted feature vectors with the corresponding load degree labels to form a sound feature sample data set.

[0042] Based on the sound feature sample data set, build a machine learning classification model. Exemplarily, such as a support vector machine (SVM), a random forest (Random Forest) or a neural network model, and train it using the sound feature sample data to finally obtain a sound data classification model.

[0043] When new working sound data is subsequently collected, first perform segmentation processing in the same way, then extract its features through the feature extraction model, and then input them into the trained sound data classification model for prediction. In this way, the current working state of the device, such as rough turning, finish turning, cutting off, etc., can be automatically judged. Thus, the working state can be distinguished more accurately, and further the energy consumption of industrial equipment can be predicted more accurately.

[0044] Step S03): Set sampling points daily, calculate the sum of the energy consumption powers associated with the working states of all devices at the sampling point moments, and record it as the predicted power.

[0045] Set multiple sampling points within a one-day time range. For example, set a sampling point every 15 minutes or 30 minutes. According to the monitored device monitoring video 11 and working sound data, obtain the working state of the industrial equipment at the sampling points. According to the energy consumption power associated with the industrial equipment in this working state. For example, if at a sampling point moment, the CNC lathe is in the rough turning state, the corresponding associated energy consumption is 8 kilowatts. Then calculate the sum of the energy consumption powers of all industrial equipment, denoted as the predicted power. Compare the predicted power with the actually collected regional energy consumption data to obtain the sampling point difference value.

[0046] Since for the same working state of the same industrial equipment, its energy consumption power is also different. For example, in the rough turning working state, it is related not only to the feed rate but also to the material being cut. However, in a mass production machining workshop, within a period of time for each process, specifically for a batch of products, each process has the same cutting parameters. That is, the cutting parameters for rough cutting are the same on one device and may be different on another device. And usually, on one batch of products, the same device only processes workpieces of one or several materials. Even if the same device processes workpieces of different materials and has different cutting parameters, the technical solution described in this specification can still achieve a relatively high prediction accuracy of energy consumption power in an average energy consumption power manner.

[0047] Step S04) Calculate the difference between the regional energy consumption data at the sampling point and the predicted power, denoted as the sampling point difference value, and the sum of all sampling point difference values is denoted as the total difference value. For example, if at a sampling point, the total predicted energy consumption based on the device state is 480 kWh, while the actually measured regional energy consumption is 430 kWh, then the difference value at this sampling point is 50 kWh.

[0048] Step S05) Continuously adjust the energy consumption power associated with each working state of each device until the total difference value is less than the preset value.

[0049] Adjusting the associated energy consumption power involves an iterative optimization process that can ultimately reduce the total difference value until it is below a preset threshold. Initially, the energy consumption power may be an estimated value based on device specifications, historical data, or a preliminary model. As more real-time data is collected, the system can calibrate these estimates more precisely. For example, if it is repeatedly observed that the actual energy consumption of a certain device in a certain working state is always higher than the predicted value, the system will correspondingly increase the estimated value of the energy consumption power in that state. Conversely, if the actual energy consumption continues to be lower than the predicted value, the corresponding estimated value will be adjusted downward. This adjustment process may be automatically completed using algorithms such as the least mean square (LMS) algorithm or other optimization algorithms to gradually approach the optimal solution, so that the total difference value meets the preset accuracy requirements. By finely adjusting the energy consumption power, it is ensured that the prediction model can reflect the actual situation as accurately as possible, thereby improving the accuracy and reliability of the entire intelligent monitoring system for industrial equipment energy consumption.

[0050] Step S06): Obtain the monitoring result according to the working state of each device recognized in real time and the associated energy consumption power.

[0051] After completing the calculation of the difference values at all sampling points and making the total difference value meet the preset standard by adjusting the energy consumption power associated with each device in different working states, the system enters the real-time monitoring stage. At this time, the status of each device will be continuously monitored. First, the current working state of each device is recognized in real time, and the corresponding energy consumption power in this state is automatically matched, and then the energy consumption of the entire monitoring area 10 is summarized and generated. On the other hand, the monitoring result can also be used as feedback information for further continuous optimization of the model. For example, if it is found that the actual energy consumption of some devices continuously deviates from the predicted value, the accuracy of the system can be improved through the parameter adjustment process.

[0052] On the other hand, this specification provides an intelligent monitoring system for industrial equipment energy consumption. Please refer to the appendix Figure 4 , including: The acquisition module 100 acquires the area monitoring video, area energy consumption data, and the working sound data of each device in the monitoring area 10, and cuts out the device monitoring video 11 of each device area from the area monitoring video; The recognition module 200 recognizes the working state of each device according to the device monitoring video 11 and the working sound data of each device, and associates an initial energy consumption power with each working state of each device; The first calculation module 300 sets sampling points daily and calculates the sum of the energy consumption powers associated with the working states of all devices at the sampling point moments, denoted as the predicted power; The second calculation module 400 calculates the difference between the area energy consumption data and the predicted power at the sampling point, denoted as the sampling point difference value, and the sum of all sampling point difference values is denoted as the total difference value; Adjustment module 500 continuously adjusts the power consumption associated with each operating state of each device until the total difference value is less than a preset value; Monitoring module 600 obtains a monitoring result according to the operating state of each device recognized in real time and the associated power consumption.

[0053] Please refer to Figure 5 the schematic structural diagram of an electronic device provided by an embodiment of this specification shown.

[0054] As Figure 5 shown, the electronic device 1100 may include: at least one processor 1101, at least one network interface 1104, a user interface 1103, a memory 1105, and at least one communication bus 1102. Among them, the communication bus 1102 can be used to realize the connection and communication of the above components. Among them, the user interface 1103 may include buttons, and the optional user interface may further include a standard wired interface and a wireless interface. Among them, the network interface 1104 may include, but is not limited to, a Bluetooth module, an NFC module, a Wi-Fi module, etc. Among them, the processor 1101 may include one or more processing cores. The processor 1101 connects various parts within the entire electronic device 1100 through various interfaces and lines, and executes various functions of the routing device 1100 and processes data by running or executing instructions, programs, code sets, or instruction sets stored in the memory 1105, and by calling data stored in the memory 1105. Optionally, the processor 1101 may be implemented in at least one of the hardware forms of DSP, FPGA, and PLA. The processor 1101 may integrate one or a combination of several of CPU, GPU, and modem, etc. Among them, the CPU mainly processes the operating system, user interface, application programs, etc.; the GPU is responsible for rendering and drawing the content to be displayed on the display screen; the modem is used to process wireless communication.

[0055] It can be understood that the above modem may not be integrated into the processor 1101 and may be implemented separately by a chip.

[0056] Among them, the memory 1105 may include RAM or ROM. Optionally, the memory 1105 includes a non-transitory computer-readable medium. The memory 1105 can be used to store instructions, programs, codes, code sets, or instruction sets. The memory 1105 may include a program storage area and a data storage area. Among them, the program storage area can store instructions for implementing the operating system, instructions for at least one function (such as touch function, sound playback function, image playback function, etc.), instructions for implementing the above-mentioned method embodiments, etc.; the data storage area can store the data involved in the above-mentioned method embodiments. Optionally, the memory 1105 may also be at least one storage device located far from the aforementioned processor 1101. The memory 1105, as a computer storage medium, may include an operating system, a network communication module, a user interface module, and application programs. The processor 1101 can be used to call the application programs stored in the memory 1105 and execute the methods in the above-mentioned multiple embodiments.

[0057] The embodiments of this specification also provide a computer-readable storage medium. Instructions are stored in the computer-readable storage medium. When the instructions are run on a computer or a processor, the computer or the processor is caused to execute multiple steps in the above-mentioned embodiments. If the respective component modules of the above-mentioned electronic device are implemented in the form of software functional units and sold or used as independent products, they can be stored in the computer-readable storage medium.

[0058] The embodiments of this specification also provide a computer program product, including a computer program. When the computer program is executed by a processor, multiple steps in the above-mentioned embodiments are implemented.

[0059] Without conflict, the technical features in this embodiment and the implementation solutions can be combined arbitrarily.

[0060] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware, or any combination thereof. When implemented using software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes a plurality of computer instructions. When the computer program instructions are loaded and executed on a computer, the processes or functions described in the embodiments of this specification are generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium or transmitted through the computer-readable storage medium. The computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center by wire (such as coaxial cable, optical fiber, Digital Subscriber Line (DSL)) or wirelessly (such as infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that the computer can access or a data storage device such as a server or data center that includes a plurality of available media integrated. The available medium can be a magnetic medium (for example, a floppy disk, a hard disk, a magnetic tape), an optical medium (for example, a Digital Versatile Disc (DVD)), or a semiconductor medium (for example, a Solid State Disk (SSD)), etc.

[0061] When implemented by hardware or firmware, the foregoing method flow is programmed into a hardware circuit to obtain a corresponding hardware circuit structure and implement the corresponding function. For example, a Programmable Logic Device (PLD) (such as a Field Programmable Gate Array (FPGA)) is such an integrated circuit, and its logic function is determined by the user programming the device. A designer can program a digital system "integrated" on a PLD by himself / herself, without having to ask a chip manufacturer to design and manufacture a dedicated integrated circuit chip. Moreover, nowadays, instead of manually fabricating an integrated circuit chip, this programming is mostly implemented using "logic compiler" software, which is similar to the software compiler used in program development and writing. The original code before compilation also has to be written in a specific programming language, which is called a Hardware Description Language (HDL), and there is not only one kind of HDL, but many kinds. Those skilled in the art should also be clear that only by slightly logically programming the method flow with the above several hardware description languages and programming it into an integrated circuit, it is easy to obtain a hardware circuit that implements the logic method flow.

[0062] The embodiments described above are merely described in the preferred embodiment mode of this specification, and do not limit the scope of this specification. Without departing from the design spirit of this specification, various deformations and improvements made by those of ordinary skill in the art to the technical solutions of this specification shall fall within the protection scope determined by the claims of this specification.

Claims

1. An intelligent monitoring method for the energy consumption of industrial equipment, characterized in that, Including the steps: Collect the area monitoring video, area energy consumption data, and working sound data of each device in the monitoring area, and segment the device monitoring video of each device area from the area monitoring video; Based on the device monitoring video and working sound data of each device, identify the working state of each device, and associate an initial energy consumption power with each working state of each type of device; Set sampling points daily, calculate the sum of the energy consumption powers associated with the working states of all devices at the sampling point times, and record it as the predicted power; Calculate the difference between the area energy consumption data at the sampling point and the predicted power, and record it as the sampling point difference value. The sum of all sampling point difference values is recorded as the total difference value; Continuously adjust the energy consumption power associated with each working state of each type of device until the total difference value is less than the preset value; Obtain the monitoring result based on the working state of each device identified in real time and the associated energy consumption power.

2. The intelligent monitoring method for industrial equipment energy consumption according to claim 1, characterized in that: The method for identifying the working state of each device based on the device monitoring video and working sound data of each device includes: Identify the moving parts of the device based on the device monitoring video to obtain the moving part time sequence table; Segment the device monitoring video according to the moving part time sequence table, and each segment corresponds to a working state; Assign a unique identification name to each working state, and use the identification name as the working state of the segment; Read the working sound data corresponding to each working state of the device, extract the features of the working sound data, and classify the sound data according to the features; When there are multiple classifications of the working sound data corresponding to the working state, associate a suffix number with each classification of the sound data; Split the working state into multiple working states according to the classification of the sound data, and associate the identification name and the corresponding suffix number.

3. The intelligent monitoring method for industrial equipment energy consumption according to claim 2, characterized in that: The method for identifying the moving parts of the device based on the device monitoring video to obtain the moving part time sequence table includes: Read the device monitoring video containing the actions of all moving parts of the device, and receive the range annotation and part name annotation of the moving parts manually marked; Establish a part image recognition model according to the range annotation and part name annotation; Identify the parts in each frame according to the frame image of the device monitoring video and the part image recognition model; Judge whether the part is moving according to the range of the part in each frame to obtain the moving parts; The part names and action time sequences of all identified moving parts constitute the moving part time sequence table.

4. The intelligent monitoring method for industrial equipment energy consumption according to claim 3, characterized in that: The method for establishing a part image recognition model according to the range annotation and part name annotation includes: Obtain the image of the part according to the range annotation, associate the image with the part name to obtain the sample data; Establish an image recognition model, and train the image recognition model with the sample data; Obtain the part image recognition model according to the trained image recognition model.

5. The intelligent monitoring method for industrial equipment energy consumption according to claim 3, wherein collect the device monitoring videos from multiple angles; The method for establishing a component image recognition model according to the range annotation and component name annotation includes: Obtain images of the component from multiple angles according to the range annotation, associate the images with the component name, and obtain sample data; Establish an image recognition model and train the image recognition model using the sample data; Obtain a component image recognition model according to the trained image recognition model.

6. The intelligent monitoring method for industrial equipment energy consumption according to any one of claims 2 to 5, wherein The method for extracting the characteristics of the working sound data and classifying the sound data according to the characteristics includes: Segment the working sound data according to a preset time length to obtain multiple sound sample data; Establish an autoencoder model and train the autoencoder model using the sound sample data; Obtain a feature extraction model according to the autoencoder model; Extract the characteristics of the working sound data using the feature extraction model; Receive the load degree annotation added manually as an associated label to obtain sound feature sample data; Establish and train a machine learning model using the sound feature sample data to obtain a sound data classification model; Extract the characteristics of the subsequently collected working sound data and classify the sound data according to the sound data classification model.

7. An intelligent monitoring system for the energy consumption of industrial equipment, characterized in that, It includes: A collection module that collects the area monitoring video, area energy consumption data of the monitoring area, and the working sound data of each device, and cuts out the device monitoring video of each device area from the area monitoring video; An identification module that identifies the working state of each device according to the device monitoring video and working sound data of each device, and associates an initial energy consumption power with each working state of each device; A first calculation module that sets sampling points daily and calculates the sum of the energy consumption powers associated with the working states of all devices at the sampling point moments, which is recorded as the predicted power; A second calculation module that calculates the difference between the area energy consumption data and the predicted power at the sampling point, which is recorded as the sampling point difference value, and the sum of all sampling point difference values is recorded as the total difference value; An adjustment module that continuously adjusts the energy consumption power associated with each working state of each device until the total difference value is less than a preset value; A monitoring module that obtains a monitoring result according to the working state of each device recognized in real time and the associated energy consumption power.

8. An electronic device, characterized in that, It includes a processor and a memory; The processor is connected to the memory; The memory is used to store executable program codes; The processor runs the program corresponding to the executable program code by reading the executable program code stored in the memory to execute the method according to any one of claims 1 - 6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, The computer program, when executed by the processor, implements the method according to any one of claims 1 - 6.

10. A computer program product, comprising a computer program, characterized in that, The computer program, when executed by the processor, implements the method according to any one of claims 1 - 6.

Images